Upload 6 files

app.py

@@ -1,15 +1,17 @@
 from fastapi import FastAPI, Request
+from fastapi.responses import StreamingResponse
 from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import HTMLResponse, StreamingResponse
+from typing import List, Dict, Any, Optional
 from pydantic import BaseModel
-from typing import List, Optional, Union
-import requests
-import time
+import asyncio
+import httpx
 
+from config import cookies, headers
+from prompts import ChiplingPrompts
 
 app = FastAPI()
 
-# CORS
+# Add CORS middleware
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
@@ -18,81 +20,111 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
+# Define request model
+class ChatRequest(BaseModel):
+    message: str
+    messages: List[Dict[Any, Any]]
+    model: Optional[str] = "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
 
+async def generate(json_data: Dict[str, Any]):
+    max_retries = 5
+    for attempt in range(max_retries):
+        async with httpx.AsyncClient(timeout=None) as client:
+            try:
+                request_ctx = client.stream(
+                    "POST",
+                    "https://api.together.ai/inference",
+                    cookies=cookies,
+                    headers=headers,
+                    json=json_data
+                )
+
+                async with request_ctx as response:
+                    if response.status_code == 200:
+                        async for line in response.aiter_lines():
+                            if line:
+                                yield f"{line}\n"
+                        return
+                    elif response.status_code == 429:
+                        if attempt < max_retries - 1:
+                            await asyncio.sleep(0.5)
+                            continue
+                        yield "data: [Rate limited, max retries]\n\n"
+                        return
+                    else:
+                        yield f"data: [Unexpected status code: {response.status_code}]\n\n"
+                        return
+            except Exception as e:
+                yield f"data: [Connection error: {str(e)}]\n\n"
+                return
 
-class MessageContent(BaseModel):
-    type: str
-    text: str
-
+    yield "data: [Max retries reached]\n\n"
 
-class ChatMessage(BaseModel):
-    role: str
-    content: Union[str, List[MessageContent]]
+@app.get("/")
+async def index():
+    return {"status": "ok"}
 
+@app.post("/chat")
+async def chat(request: ChatRequest):
+    current_messages = request.messages.copy()
+    
+    # Handle both single text or list content
+    if request.messages and isinstance(request.messages[-1].get('content'), list):
+        current_messages = request.messages
+    else:
+        current_messages.append({
+            'content': [{
+                'type': 'text',
+                'text': request.message
+            }],
+            'role': 'user'
+        })
 
-class ChatRequest(BaseModel):
-    message: str
-    messages: List[ChatMessage]
-    model: Optional[str] = "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
+    json_data = {
+        'model': request.model,
+        'max_tokens': None,
+        'temperature': 0.7,
+        'top_p': 0.7,
+        'top_k': 50,
+        'repetition_penalty': 1,
+        'stream_tokens': True,
+        'stop': ['<|eot_id|>', '<|eom_id|>'],
+        'messages': current_messages,
+        'stream': True,
+    }
 
+    return StreamingResponse(generate(json_data), media_type='text/event-stream')
 
-cookies = {
-    'intercom-id-evnv2y8k': 'fea4d452-f9be-42e0-93e3-1e47a3836362',
-    'intercom-device-id-evnv2y8k': '2bb3e469-0159-4b6b-a33e-1aea4b51ccb1',
-    '__stripe_mid': 'e0f7c1ba-56c6-44d4-ba1d-cf4611453eb43cf922',
-    'state-csrf': '6f2o8nqgee2dfqdmhaxipe',
-    'together_auth_cookie': '%7B%22expires%22%3A%222026-04-09T15%3A14%3A08.985Z%22%2C%22session%22%3A%220eae08c6fd1b79a22476a317d440a2104d74cd3ba333e40771b5ce50a90784297eb82eff36263debca2ee0658abe3e43cab97f87794421111d4bdec56b43dd2595ee22a165c123ba3d0f807759555b5f6d3f51b7c248e7cefcdf0f0b897f62b25b2a569e2cb89633032f15dca9818f39ed49f3ac2d7e0bc3d24517c62c78b1e4%22%7D',
-    '__stripe_sid': '979e00a2-06ed-45be-9a95-88d7e7580f625ccce4',
-    'intercom-session-evnv2y8k': 'TzZzSzBNRG8xdHJtTVprMm1zUXFob0M2ekhFV3VmeDZFcW5UVldlYmFYc3RsRjFmdWJidjU1ZXVSZzNOSW9QTE82OUx6anlvMWVncmlTd2ZvOERDUXN4OUdoSEM5ZzRnQmh4d2o5S3JKeDA9LS00S3JOclNpNzU0VkVBaTNRNWhSMm93PT0=--2719775e99e920753d35527a45a6731bac5e8f8f',
-    'AMP_7112ee0414': 'JTdCJTIyZGV2aWNlSWQlMjIlM0ElMjJmY2ZmNjE3Ny00Yzg0LTRlOTItYTFhMC1kM2Y1ZjllOTFkYTglMjIlMkMlMjJ1c2VySWQlMjIlM0ElMjI2N2I1ZDkwNDNkZTIyN2Q0OGIzMWEwZTMlMjIlMkMlMjJzZXNzaW9uSWQlMjIlM0ExNzQ0MjExNjQyMjEwJTJDJTIyb3B0T3V0JTIyJTNBZmFsc2UlMkMlMjJsYXN0RXZlbnRUaW1lJTIyJTNBMTc0NDIxMTc1ODAwOSUyQyUyMmxhc3RFdmVudElkJTIyJTNBMjMyJTJDJTIycGFnZUNvdW50ZXIlMjIlM0E1JTdE',
-}
-
-headers = {
-    'accept': 'application/json',
-    'accept-language': 'en-US,en;q=0.9,ja;q=0.8',
-    'authorization': 'Bearer 4d900964e385651ea685af6f6cd5573a17b421f50657f73f903525177915a7e2',
-    'content-type': 'application/json',
-    'priority': 'u=1, i',
-    'sec-ch-ua': '"Google Chrome";v="135", "Not-A.Brand";v="8", "Chromium";v="135"',
-    'sec-ch-ua-mobile': '?0',
-    'sec-ch-ua-platform': '"macOS"',
-    'sec-fetch-dest': 'empty',
-    'sec-fetch-mode': 'cors',
-    'sec-fetch-site': 'same-origin',
-    'x-stainless-arch': 'unknown',
-    'x-stainless-lang': 'js',
-    'x-stainless-os': 'Unknown',
-    'x-stainless-package-version': '0.11.1',
-    'x-stainless-retry-count': '0',
-    'x-stainless-runtime': 'browser:chrome',
-    'x-stainless-runtime-version': '135.0.0',
-    'referer': 'https://api.together.ai/playground/v2/chat/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8',
-}
-
-
-@app.get("/", response_class=HTMLResponse)
-async def index(request: Request):
-    return {"status":"running"}
 
+@app.post("/generate-modules")
+async def generate_modules(request: Request):
+    data = await request.json()
+    search_query = data.get("searchQuery")
 
-@app.post("/chat")
-async def chat(request_data: ChatRequest):
-    user_input = request_data.message
-    messages = request_data.messages
-    model = request_data.model
+    if not search_query:
+        return {"error": "searchQuery is required"}
 
-    current_messages = messages.copy()
+    system_prompt = ChiplingPrompts.generateModules(search_query)
 
-    if messages and isinstance(messages[-1].content, list):
-        current_messages = messages
-    else:
-        current_messages.append(ChatMessage(
-            role="user",
-            content=[MessageContent(type="text", text=user_input)]
-        ))
+    current_messages = [
+        {
+            'role': 'system',
+            'content': [{
+                'type': 'text',
+                'text': system_prompt
+            }]
+        },
+        {
+            'role': 'user',
+            'content': [{
+                'type': 'text',
+                'text': search_query
+            }]
+        }
+    ]
 
     json_data = {
-        'model': model,
+        'model': "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
         'max_tokens': None,
         'temperature': 0.7,
         'top_p': 0.7,
@@ -100,39 +132,51 @@ async def chat(request_data: ChatRequest):
         'repetition_penalty': 1,
         'stream_tokens': True,
         'stop': ['<|eot_id|>', '<|eom_id|>'],
-        'messages': [m.dict() for m in current_messages],
+        'messages': current_messages,
         'stream': True,
     }
 
-    def generate():
-        max_retries = 5
-
-        for attempt in range(max_retries):
-            response = requests.post(
-                'https://api.together.ai/inference',
-                cookies=cookies,
-                headers=headers,
-                json=json_data,
-                stream=True
-            )
-
-            if response.status_code == 200:
-                for line in response.iter_lines():
-                    if line:
-                        decoded_line = line.decode('utf-8')
-                        if decoded_line.startswith("data: "):
-                            yield f"{decoded_line}\n\n"
-                return
-            elif response.status_code == 429:
-                if attempt < max_retries - 1:
-                    time.sleep(0.5)
-                    continue
-                yield 'data: {"error": "Rate limited, maximum retries reached"}\n\n'
-                return
-            else:
-                yield f'data: {{"error": "Unexpected status code: {response.status_code}"}}\n\n'
-                return
+    return StreamingResponse(generate(json_data), media_type='text/event-stream')
+
+
+@app.post("/generate-topics")
+async def generate_topics(request: Request):
+    data = await request.json()
+    search_query = data.get("searchQuery")
+
+    if not search_query:
+        return {"error": "searchQuery is required"}
+
+    system_prompt = ChiplingPrompts.generateTopics(search_query)
+
+    current_messages = [
+        {
+            'role': 'system',
+            'content': [{
+                'type': 'text',
+                'text': system_prompt
+            }]
+        },
+        {
+            'role': 'user',
+            'content': [{
+                'type': 'text',
+                'text': search_query
+            }]
+        }
+    ]
 
-        yield 'data: {"error": "Maximum retries reached"}\n\n'
+    json_data = {
+        'model': "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
+        'max_tokens': None,
+        'temperature': 0.7,
+        'top_p': 0.7,
+        'top_k': 50,
+        'repetition_penalty': 1,
+        'stream_tokens': True,
+        'stop': ['<|eot_id|>', '<|eom_id|>'],
+        'messages': current_messages,
+        'stream': True,
+    }
 
-    return StreamingResponse(generate(), media_type="text/event-stream")
+    return StreamingResponse(generate(json_data), media_type='text/event-stream')

config.py

@@ -0,0 +1,32 @@
+cookies = {
+    'intercom-id-evnv2y8k': 'fea4d452-f9be-42e0-93e3-1e47a3836362',
+    'intercom-device-id-evnv2y8k': '2bb3e469-0159-4b6b-a33e-1aea4b51ccb1',
+    '__stripe_mid': 'e0f7c1ba-56c6-44d4-ba1d-cf4611453eb43cf922',
+    'state-csrf': '6f2o8nqgee2dfqdmhaxipe',
+    'together_auth_cookie': '%7B%22expires%22%3A%222026-04-09T15%3A14%3A08.985Z%22%2C%22session%22%3A%220eae08c6fd1b79a22476a317d440a2104d74cd3ba333e40771b5ce50a90784297eb82eff36263debca2ee0658abe3e43cab97f87794421111d4bdec56b43dd2595ee22a165c123ba3d0f807759555b5f6d3f51b7c248e7cefcdf0f0b897f62b25b2a569e2cb89633032f15dca9818f39ed49f3ac2d7e0bc3d24517c62c78b1e4%22%7D',
+    '__stripe_sid': '979e00a2-06ed-45be-9a95-88d7e7580f625ccce4',
+    'intercom-session-evnv2y8k': 'TzZzSzBNRG8xdHJtTVprMm1zUXFob0M2ekhFV3VmeDZFcW5UVldlYmFYc3RsRjFmdWJidjU1ZXVSZzNOSW9QTE82OUx6anlvMWVncmlTd2ZvOERDUXN4OUdoSEM5ZzRnQmh4d2o5S3JKeDA9LS00S3JOclNpNzU0VkVBaTNRNWhSMm93PT0=--2719775e99e920753d35527a45a6731bac5e8f8f',
+    'AMP_7112ee0414': 'JTdCJTIyZGV2aWNlSWQlMjIlM0ElMjJmY2ZmNjE3Ny00Yzg0LTRlOTItYTFhMC1kM2Y1ZjllOTFkYTglMjIlMkMlMjJ1c2VySWQlMjIlM0ElMjI2N2I1ZDkwNDNkZTIyN2Q0OGIzMWEwZTMlMjIlMkMlMjJzZXNzaW9uSWQlMjIlM0ExNzQ0MjExNjQyMjEwJTJDJTIyb3B0T3V0JTIyJTNBZmFsc2UlMkMlMjJsYXN0RXZlbnRUaW1lJTIyJTNBMTc0NDIxMTc1ODAwOSUyQyUyMmxhc3RFdmVudElkJTIyJTNBMjMyJTJDJTIycGFnZUNvdW50ZXIlMjIlM0E1JTdE',
+}
+
+headers = {
+    'accept': 'application/json',
+    'accept-language': 'en-US,en;q=0.9,ja;q=0.8',
+    'authorization': 'Bearer 4d900964e385651ea685af6f6cd5573a17b421f50657f73f903525177915a7e2',
+    'content-type': 'application/json',
+    'priority': 'u=1, i',
+    'sec-ch-ua': '"Google Chrome";v="135", "Not-A.Brand";v="8", "Chromium";v="135"',
+    'sec-ch-ua-mobile': '?0',
+    'sec-ch-ua-platform': '"macOS"',
+    'sec-fetch-dest': 'empty',
+    'sec-fetch-mode': 'cors',
+    'sec-fetch-site': 'same-origin',
+    'x-stainless-arch': 'unknown',
+    'x-stainless-lang': 'js',
+    'x-stainless-os': 'Unknown',
+    'x-stainless-package-version': '0.11.1',
+    'x-stainless-retry-count': '0',
+    'x-stainless-runtime': 'browser:chrome',
+    'x-stainless-runtime-version': '135.0.0',
+    'referer': 'https://api.together.ai/playground/v2/chat/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8',
+}

dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

prompts.py

@@ -0,0 +1,58 @@
+class ChiplingPrompts:
+
+    def generateModules(searchQuery):
+       prompt =  '''
+            Generate a structured learning path for the topic: "${searchQuery}".
+
+            Please provide all the modules (chapters) associated with the topic to cover all the content for the respective topic, with each module having:
+            - A title
+            - all the topics that are specifically related to that module
+            - generate more than 4 topics for each module
+            
+            For each topic, include:
+            - A title
+            - A relevance score (1-10)
+            - A short description (2-3 sentences)
+            
+            Format the response as JSON that matches this TypeScript interface:
+            {
+                modules: Array<{
+                title: string;
+                topics: Array<{
+                    title: string;
+                    relevance: number;
+                    description: string;
+                }>
+                }>
+            }
+            
+            Each module should build on the previous one, progressively increasing in complexity or depth.
+            Only respond with the JSON data.`
+        '''
+       return prompt
+    
+    def generateTopics(searchQuery):
+        prompt =  '''
+            Generate detailed information about the topic: "${searchQuery}".
+            Please include:
+            - A comprehensive content section (3-4 paragraphs)
+            - 2-3 subtopics, each with title, description, and content
+            - 3-5 references or further reading suggestions
+            
+            Format the response as JSON that matches this TypeScript interface:
+            {
+                title: string;
+                relevance: number;
+                description: string;
+                content: string;
+                subtopics: Array<{
+                title: string;
+                description: string;
+                content: string;
+                }>;
+                references: string[];
+            }
+            
+            Only respond with the JSON data.
+        '''
+        return prompt

requirements.txt

@@ -1,9 +1,5 @@
-beautifulsoup4==4.13.3
-curl_cffi==0.7.4
 fastapi==0.115.12
-instabot==0.117.0
-praw==7.8.1
-Pyrebase4==4.8.0
-tenacity==9.0.0
-tweepy==4.14.0
-uvicorn
+httpx==0.28.1
+pydantic==2.11.3
+Requests==2.32.3
+uvicorn[standard]

test.py

@@ -0,0 +1,71 @@
+import requests
+import json
+
+# url = "http://localhost:8000/chat"  # Change to your server address if different
+
+# payload = {
+#     "message": "Hello, how are you?",
+#     "messages": [
+#         {
+#             "role": "system",
+#             "content": [
+#                 {
+#                     "type": "text",
+#                     "text": "You are a helpful assistant."
+#                 }
+#             ]
+#         }
+#     ],
+#     "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
+# }
+
+# headers = {
+#     "Content-Type": "application/json"
+# }
+
+# response = requests.post(url, data=json.dumps(payload), headers=headers, stream=True)
+
+# if response.status_code == 200:
+#     print("Streaming response:\n")
+#     try:
+#         for line in response.iter_lines(decode_unicode=True):
+#             if line:
+#                 print(line)
+#     except KeyboardInterrupt:
+#         print("\nStopped streaming.")
+# else:
+#     print("Error:", response.status_code)
+#     print(response.text)
+
+
+url = "http://localhost:8000/generate-topics"
+payload = {
+    "searchQuery": "Introduction linear integrated circuits"
+}
+headers = {
+    "Content-Type": "application/json"
+}
+
+response = requests.post(url, data=json.dumps(payload), headers=headers, stream=True)
+
+if response.status_code == 200:
+    print("Streaming response:\n")
+    try:
+        for line in response.iter_lines(decode_unicode=True):
+            if line:
+                if line.startswith("data: "):
+                    # Parse the JSON data after "data: "
+                    try:
+                        json_data = json.loads(line[6:])  # Skip "data: " prefix
+                        if "choices" in json_data and json_data["choices"]:
+                            if "text" in json_data["choices"][0]:
+                                print(json_data["choices"][0]["text"], end="", flush=True)
+                    except json.JSONDecodeError:
+                        # Handle special case for [DONE]
+                        if line[6:] == "[DONE]":
+                            break
+    except KeyboardInterrupt:
+        print("\nStopped streaming.")
+else:
+    print("Error:", response.status_code)
+    print(response.text)